Overview ¶

This document lists the layers (or operators) which can be imported and converted. Supported operators allow to address a large range of classical topologies targeting a Mobile or IoT resource-constrained runtime environment: SqueezeNet, MobileNet V1 or V2, Inception, SSD MobileNet v1,…

Purpose of this document is to list the operators and their associated constraints or limitations, please refer to the original documentation for details on a given layer.

Keras.io 3 is supported through the Tensorflow backend with channels-last dimension ordering. Keras.io 2.0 up to version 2.15 is supported through tf_keras, while networks defined in Keras 1.x are not officially supported.
This file was automatically generated.

ST Edge AI Core version : 4.0
111 operators found
28 custom operators found

Summary table ¶

Following table contains the list of the operators that can be imported, if the constraints or limitations are met. The 28 custom operators are listed in the next table.

supported optional fused activation (or non-linearity): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign, abs, acos, acosh, asin, asinh, atan, atanh, ceil, clip, cos, cosh, erf, flexerf, exp, floor, identity, log, logistic, neg, logical_not, prelu, probit, reciprocal, relu_generic, relu_thresholded, round, sign, sin, sinh, softmax_zero, sqrt, swish, tan
supported optional fused integer activation (or non-linearity): prelu, relu, clip, lut, swish, identity, relu6
integer operation for Keras models are only supported through QKeras and Larq extensions
if an operator is not supported in integer, floating point version is used. Converters are automatically added by the code generator.

operator	data types	constraints/limitations
ops.absolute	float32	common, specific
layers.Activation	float32, int8, uint8	common, specific
layers.ActivityRegularization	float32	common, specific
layers.Add	float32	common
layers.AlphaDropout	float32	common, specific
ops.arccos	float32	common, specific
ops.arccosh	float32	common, specific
ops.arcsin	float32	common, specific
ops.arcsinh	float32	common, specific
ops.arctan	float32	common, specific
ops.arctan2	float32	common, specific
ops.arctanh	float32	common, specific
ops.argmax	float32	common, specific
ops.argmin	float32	common, specific
layers.Average	float32	common
layers.AveragePooling1D	float32, int8, uint8	common, specific
layers.AveragePooling2D	float32, int8, uint8	common, specific
layers.BatchNormalization	float32	common, specific
layers.Bidirectional	float32	common, specific
ops.ceil	float32	common, specific
layers.Concatenate	float32	common, specific
layers.Conv1D	float32, int8, uint8	common, specific
layers.Conv1DTranspose	float32, int8, uint8	common, specific
layers.Conv2D	float32, int8, uint8	common, specific
layers.Conv2DTranspose	float32, int8, uint8	common, specific
ops.cos	float32	common, specific
ops.cosh	float32	common, specific
layers.Cropping1D	float32	common
layers.Cropping2D	float32	common
CustomDoReFa	float32, int8, uint8	common
CustomDoReFaQuantizer	float32, int8, uint8	common
layers.Lambda	float32	specific
layers.Dense	float32, int8, uint8	common, specific
layers.DepthwiseConv2D	float32, int8, uint8	common, specific
ops.divide	float32	common, specific
layers.Dropout	float32	common, specific
layers.ELU	float32, int8, uint8	common
ops.equal	float32, bool	common, specific
ops.erf	float32	common, specific
layers.Flatten	float32, int8, uint8	common, specific
ops.floor	float32	common, specific
ops.floor_divide	float32	common, specific
layers.GaussianDropout	float32	common, specific
layers.GaussianNoise	float32	common, specific
layers.GlobalAveragePooling1D	float32, int8, uint8	common
layers.GlobalAveragePooling2D	float32, int8, uint8	common
layers.GlobalMaxPooling1D	float32, int8, uint8	common
layers.GlobalMaxPooling2D	float32, int8, uint8	common
ops.greater	float32, bool	common
ops.greater_equal	float32	common, specific
layers.GRU	float32	common, specific
ops.hard_silu	float32	common, specific
layers.InputLayer	float32, int8, uint8	common, specific
layers.LayerNormalization	float32	common
layers.LeakyReLU	float32, int8, uint8	common
ops.leaky_relu	float32	common, specific
ops.less	float32, bool	common, specific
ops.less_equal	float32	common, specific
ops.log	float32	common, specific
ops.logical_and	float32	common, specific
ops.logical_not	float32	common, specific
ops.logical_or	float32	common, specific
ops.logical_xor	float32	common, specific
layers.LSTM	float32	common, specific
ops.maximum	float32	common, specific
layers.MaxPooling1D	float32, int8, uint8	common, specific
layers.MaxPooling2D	float32, int8, uint8	common, specific
ops.minimum	float32	common, specific
ops.mod	float32	common, specific
layers.Multiply	float32	common
ops.negative	float32	common, specific
ops.not_equal	float32	common, specific
layers.Permute	float32, int8, uint8	common, specific
layers.PReLU	float32, int8, uint8	common, specific
qkeras.QActivation	float32, int8, binary	common, specific
qkeras.QBatchNormalization	float32, int8, binary	common, specific
qkeras.QConv1D	float32, int8, binary	common, specific
qkeras.QConv2D	float32, int8, binary	common, specific
qkeras.QConv2DTranspose	float32, int8, binary	common, specific
qkeras.QDense	float32, int8, binary	common, specific
qkeras.QDepthwiseConv2D	float32, int8, binary	common, specific
larq.layers.QuantConv2D	float32, int8, binary	common, specific
larq.layers.QuantDense	float32, int8, binary	common, specific
larq.layers.QuantDepthwiseConv2D	float32, int8, binary	common, specific
ops.relu	float32	common, specific
layers.ReLU	float32, int8, uint8	common
ops.relu6	float32	common, specific
layers.RepeatVector	float32	common
layers.Reshape	float32, int8, uint8	common
ops.round	float32	common, specific
ops.rsqrt	float32	common, specific
ops.selu	float32	common, specific
layers.SeparableConv1D	float32, int8, uint8	common, specific
layers.SeparableConv2D	float32, int8, uint8	common, specific
ops.sign	float32	common, specific
ops.sin	float32	common, specific
layers.Softmax	float32	common, specific
layers.SpatialDropout1D	float32	common, specific
layers.SpatialDropout2D	float32	common, specific
ops.sqrt	float32	common, specific
STCustomDoReFa	float32, int8, uint8	common
layers.Subtract	float32	common
ops.tan	float32	common, specific
ops.tanh	float32	common, specific
layers.TFOpLambda	float32	specific
layers.ThresholdedReLU	float32, int8, uint8	common
layers.TimeDistributed	float32	common, specific
layers.UpSampling1D	float32	common
layers.UpSampling2D	float32	common
layers.ZeroPadding1D	float32, int8, uint8	common
layers.ZeroPadding2D	float32, int8, uint8	common

Custom operators ¶

Following table contains the list of the custom Keras 2 operators that can be imported.

Operator	Data types	Constraints/Limitations
Abs	float32	specific
Acos	float32	specific
Acosh	float32	specific
Asin	float32	specific
Asinh	float32	specific
Atan	float32	specific
Atanh	float32	specific
Ceil	float32	specific
Clip	float32	specific
Cos	float32	specific
Exp	float32	specific
Fill	float32	common, specific
FloorDiv	float32	specific
FloorMod	float32	specific
Log	float32	specific
Pow	float32	specific
Reciprocal	float32	specific
Reshape	float32, int8, uint8	common, specific
Round	float32	specific
Shape	float32, int8, uint8, int32	common, specific
Sign	float32	specific
Sin	float32	specific
Split	float32, int8, uint8	common, specific
Sqrt	float32	specific
Square	float32	specific
Tanh	float32	specific
Unpack	float32, int8, uint8	common, specific
Where	float32, int8, uint8, int16, uint16, int32, uint32, bool	common, specific

Common constraints ¶

input and output tensors must be not dynamic.
- variable-length batch dimension (i.e. (None,)) is considered as equal to 1
- must not be greater than 6D
- dimension must be in the range [0, 65536[
- batch dimension is partially supported in the axis/axes parameters
data type for the weights/activations tensors must be:
- float32, int8, uint8
- only int32 for the bias tensor is considered
- for some operators, bool and binary types are also supported
1D operator is mapped on the respective 2D operator by adding a singleton dimension on the input: (12,3) -> (12, 1, 3)

Operators ¶

ops.absolute ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Activation ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign

Specific constraints/recommendations:

softmax is always conserved in float32, converters are added if necessary

layers.ActivityRegularization ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

layers.Add ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

layers.AlphaDropout ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

ops.arccos ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arccosh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arcsin ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arcsinh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arctan ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arctan2 ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.arctanh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.argmax ¶

input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.argmin ¶

input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Average ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

layers.AveragePooling1D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary pool sizes, provided that they are smaller than the input size

layers.AveragePooling2D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary pool sizes, provided that they are smaller than the input size

layers.BatchNormalization ¶

Performs the normalization of the input

category: normalization layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Only normalization on the last axis (channels) is supported

layers.Bidirectional ¶

Bidirectionnal wrapper for RNNs

category: recurrent layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

supported layers: LSTM, GRU and SimpleRNN
supported merge mode: concat, mul, ave and sum

ops.ceil ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Concatenate ¶

Performs concatenation of a list of inputs

category: merge operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

concatenating on the batch dimension is not supported

layers.Conv1D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
dilation factors different from 1 are not supported for int8 model

layers.Conv1DTranspose ¶

Transposed convolutional layer

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size

layers.Conv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
dilation factors different from 1 are not supported for int8 model

layers.Conv2DTranspose ¶

Transposed convolutional layer

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size

ops.cos ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.cosh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Cropping1D ¶

Crops the input

category: reshaping layer
input data types: float32
output data types: float32

layers.Cropping2D ¶

Crops the input

category: reshaping layer
input data types: float32
output data types: float32

CustomDoReFa ¶

Computes element-wise data conversion full precision to low precision, based on the scale/zeropoint parameters

category: conversion layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

CustomDoReFaQuantizer ¶

Computes element-wise data conversion full precision to low precision, based on the scale/zeropoint parameters

category: conversion layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.Lambda ¶

Wraps arbitrary expressions

category: custom layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

The wrapped operation is uncompiled, this conversion may fail if the tf operator is unsupported

layers.Dense ¶

Fully Connected operation

category: core layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

for the floating point model, weights and/or bias can be compressed during the code generation

layers.DepthwiseConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
dilation factors different from 1 are not supported for int8 model

ops.divide ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Dropout ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

layers.ELU ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

ops.equal ¶

Performs logical element-wise operation

category: eltwise operator
input data types: float32
output data types: bool

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.erf ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Flatten ¶

Flattens the non-batch input dimensions to a vector

category: Reshaping operation
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

Flatten on the batch dimension is not supported
operator is dropped during the conversion

ops.floor ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.floor_divide ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.GaussianDropout ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

layers.GaussianNoise ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

layers.GlobalAveragePooling1D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.GlobalAveragePooling2D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.GlobalMaxPooling1D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.GlobalMaxPooling2D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

ops.greater ¶

Performs logical element-wise operation

category: eltwise operator
input data types: float32
output data types: bool

ops.greater_equal ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.GRU ¶

Gated Recurrent Unit

category: recurrent layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

stateless and stateful (batch=1 only) mode support
fused activation: gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
fused recurrent activation: gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
return_state not supported

ops.hard_silu ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.InputLayer ¶

Optional placeholder for the network’s input

category: core layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

operator is dropped during the conversion

layers.LayerNormalization ¶

Apply LayerNormalization along the provided axis

category: normalization function
input data types: float32
output data types: float32

layers.LeakyReLU ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

ops.leaky_relu ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.less ¶

Performs logical element-wise operation

category: eltwise operator
input data types: float32
output data types: bool

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.less_equal ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.log ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.logical_and ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.logical_not ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.logical_or ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.logical_xor ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.LSTM ¶

Computes a multi-layer long short-term memory (LSTM) RNN to an input sequence (batch=1, timesteps, features)

category: recurrent layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

stateless and stateful (batch=1 only) mode support
in stateful mode the user is requested to define two C routines to allocate and deallocate internal layer state.
- initial state must be provided as part of the allocation routine implementation
- the two functions to implement are:
  - void _allocate_lstm_states(ai_float **states, ai_u32 size_in_bytes)
  - void _deallocate_lstm_states(ai_float **states)
fused activation: gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
fused recurrent activation: gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
return_state not supported

ops.maximum ¶

Computes the maximum (element-wise) a list of inputs

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.MaxPooling1D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary pool sizes, provided that they are smaller than the input size

layers.MaxPooling2D ¶

Downsamples the input

category: pooling layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary pool sizes, provided that they are smaller than the input size

ops.minimum ¶

Computes the minimum (element-wise) a list of inputs

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.mod ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Multiply ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

ops.negative ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.not_equal ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Permute ¶

Permutes the dimensions of the input according to a given pattern

category: reshaping layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

transposing the batch dimension is not supported

layers.PReLU ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

shared axes in PReLU supported only for the leading dimensions

qkeras.QActivation ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, binary
output data types: binary

Specific constraints/recommendations:

Custom Keras layer from QKeras framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QBatchNormalization ¶

Performs the normalization of the input

category: normalization layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

Custom Keras layer from QKeras framework
Only normalization on the last axis (channels) is supported
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QConv1D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
Custom Keras layer from QKeras framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
Custom Keras layer from QKeras framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QConv2DTranspose ¶

Transposed convolutional layer

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

Custom Keras layer from QKeras framework
Padding must be valid
Stride must be (1, 1)
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QDense ¶

category: core layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

Custom Keras layer from QKeras framework
Only 2D input shape is supported: [batch_size, input_dim]. A rank greater than 2 is not supported, Flatten layer before the QuantDense/QDense operator should be added
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

qkeras.QDepthwiseConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
Custom Keras layer from QKeras framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

larq.layers.QuantConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
Custom Keras layer from LARQ framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

larq.layers.QuantDense ¶

category: core layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

Custom Keras layer from LARQ framework
Only 2D input shape is supported: [batch_size, input_dim]. A rank greater than 2 is not supported, Flatten layer before the QuantDense/QDense operator should be added
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

larq.layers.QuantDepthwiseConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, binary
output data types: float32, int8, binary

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
Custom Keras layer from LARQ framework
For detailed information, see [Deep Quantized Neural Network [DQNN] support][STAI_CORE_DQNN] article

ops.relu ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.ReLU ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

ops.relu6 ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.RepeatVector ¶

Repeats the input n times

category: reshaping layer
input data types: float32
output data types: float32

layers.Reshape ¶

Reshapes a tensor

category: Reshaping operation
input data types: float32, int8, uint8
output data types: float32, int8, uint8

ops.round ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.rsqrt ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.selu ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.SeparableConv1D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
dilation factors different from 1 are not supported for int8 model

layers.SeparableConv2D ¶

Performs convolution operation

category: convolutional layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8
fused activations (if present): gelu, linear, relu, quantized_relu, relu_n1_to_1, relu_0_to_1, leaky_relu, relu6, elu, selu, sigmoid, hard_sigmoid, hard_swish, exponential, tanh, softmax, softplus, softsign
integer schemes: weights / activations
- Signed Symmetric / Signed Asymmetric (SSSA)
- Signed Symmetric per channel (or per-axis) / Signed Asymmetric (SSSA_CH)
- Signed Symmetric / Unsigned Asymmetric (SSUA)
- Signed Symmetric per channel (or per-axis) / Unsigned Asymmetric (SSUA_CH)
- Unsigned Asymmetric / Unsigned Asymmetric (UAUA)
- Unsigned Asymmetric per channel (or per-axis) / Unsigned Asymmetric (UAUA_CH)

Specific constraints/recommendations:

arbitrary strides, provided that they are smaller than the input size
arbitrary filter kernel sizes, provided that they are smaller than the input size
dilation factors different from 1 are not supported for int8 model

ops.sign ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.sin ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.Softmax ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

It is supported only for 1D tensor and only on the channel dimension
The value 1 is supported as the default value of the axis attribute, not the value -1

layers.SpatialDropout1D ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

layers.SpatialDropout2D ¶

Applies Dropout to the input

category: regularization layers
input data types: float32
output data types: float32

Specific constraints/recommendations:

operator is dropped during the conversion

ops.sqrt ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

STCustomDoReFa ¶

Computes element-wise data conversion full precision to low precision, based on the scale/zeropoint parameters

category: conversion layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.Subtract ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

ops.tan ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

ops.tanh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported only in Keras 3 models

layers.TFOpLambda ¶

Wraps arbitrary expressions

category: custom layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

The wrapped operation is uncompiled, this conversion may fail if the tf operator is unsupported

layers.ThresholdedReLU ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.TimeDistributed ¶

Applies a layer to every temporal slice of an input

category: wrapper layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

Supported layers: Conv2D, Dense, Flatten, MaxPooling2D, ZeroPadding2D, Dropout

layers.UpSampling1D ¶

category: resizing operation
input data types: float32
output data types: float32

layers.UpSampling2D ¶

category: resizing operation
input data types: float32
output data types: float32

layers.ZeroPadding1D ¶

Pads an input tensor

category: Reshaping layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

layers.ZeroPadding2D ¶

Pads an input tensor

category: Reshaping layer
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Custom operators ¶

Abs ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.abs

Acos ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.acos

Acosh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.acosh

Asin ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.asin

Asinh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.asinh

Atan ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.atan

Atanh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.atanh

Ceil ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.ceil

Clip ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.clip_by_value

Cos ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.cos

Exp ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.exp

Fill ¶

Generates a tensor with given value and shape

category: constant layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.fill

FloorDiv ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.floordiv

FloorMod ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.floormod

Log ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.log

Pow ¶

Performs element-wise operation

category: eltwise operator
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.pow

Reciprocal ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.reciprocal

Reshape ¶

Reshapes a tensor

category: Reshaping operation
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

related TF operator: tf.reshape
operator is dropped during the conversion

Round ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.round

Shape ¶

Returns a tensor containing the shape of the input tensor

category: Reshaping operation
input data types: float32, int8, uint8
output data types: int32

Specific constraints/recommendations:

related TF operator: tf.shape

Sign ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.sign

Sin ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.sin

Split ¶

Splits a tensor into a list of sub tensors

category: split operator
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

Only supported if the number of splits is equal to the size of the splitting dimension
related TF operator: tf.split

Sqrt ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.sqrt

Square ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.square

Tanh ¶

Applies an activation function to the input tensor

category: activation layer
input data types: float32
output data types: float32

Specific constraints/recommendations:

related TF operator: tf.math.tanh

Unpack ¶

Unpacks num tensors from values along specified axis

category: split operator
input data types: float32, int8, uint8
output data types: float32, int8, uint8

Specific constraints/recommendations:

related TF operator: tf.unpack

Where ¶

Where layer

category: generic layer
input data types: float32, int8, uint8, int16, uint16, int32, uint32, bool
output data types: float32, int8, uint8, int16, uint16, int32, uint32, bool

Specific constraints/recommendations:

related TF operator: tf.where